Biography
Hi 🤗! I am a third-year Ph.D. student at Hong Kong University of Science and Technology, advised by Prof. Ling Pan. Currently, I intern at ByteDance Seed, working on RL post-training for industry-scale (agentic) Multimodal intelligence.
I received my Bachelor’s degree in computer science at Shanghai Jiao Tong University in June 2023, advised by Prof. Weinan Zhang as a member of APEX Lab. Previously, I worked closely with Dr. Xintao Wang as an intern at Kuaishou Kling, Dr. Zhongwen Xu as an intern at Tencent, and Dr. Chenjia Bai as an intern at Shanghai AI Lab.
I am actively seeking full-time positions starting in 2027. If there are any opportunities, please reach out to me.
Feel free to contact me with email (haoran.he@connect.ust.hk) or wechat (hhr_tinner).
Research Interests
My goal is to develop an intelligent decision-making system that possesses optimality, generalizability, interpretability, and robustness. To achieve this, I primarily focus on 🤔:
- Generalist Reinforcement Learning theory and methods (RPE, RBS).
- Post-Training for Generative models (LLM reasoning:ROVER; Multimodal: GARDO, EvoSearch; World Model: DWS).
- Reinforcement Learning for real-world reasoning and decision-making (MTDiffuser, VPDD, HIB, DAERT).
📖 Service
- Conference reviewer: ICML 2024～2026, NeurIPS 2024~2026, IROS 2024, AAAI 2025~2026, ICLR 2025~2026, ICRA 2025, CVPR 2026
- Journal reviewer: TPAMI, Artificial Intelligence
🔥 News
[Jan. 2026] 🎉 ROVER has been accepted by ICLR 2026!
[Jan. 2025] 🎉 We released GARDO: Reinforcing Diffusion Models without Reward Hacking!
[Nov. 2025] 🎉 DWS (Pre-Trained Video Generative Models as World Simulators) has been accepted by AAAI 2026.
[Oct. 2025] 🎉 We released ROVER, a very simple RLVR method that can shape the future of LLM reasoning!
[June. 2025] 🎉 We released EvoSearch, a novel test-time scaling framework for both image and video generation!
[May. 2025] 🎉 RPE and SODP have been accepted by ICML 2025!
[Apr. 2025] 🎉 I have passed PhD Qualifying Exam. My slides are available here
[Mar. 2025] I gave an invited talk at MSRA.
[Feb. 2025] 🎉RBS-GFN has been accepted by ICLR 2025!
[Sep. 2024] 🎉 VPDD and CAMP have been accepted by NeurIPS 2024!
[Sep. 2024] 🎉 HIB has been accepted as CoRL 2024 oral presentation!
[May. 2024] One paper has been accepted by ICML 2024!
[Jan. 2024] One paper has been accepted by ICRA 2024!
[Sep. 2023] 🎉 Our paper (MTDiff) has been accepted by NeurIPS 2023.
[Sep. 2023] I gave a talk at RLChina.
[Jul. 2023] 🎉 I received my Bachelor’s degree from Shanghai Jiao Tong University.